INDEX

Explanations

references to machine learning techniques and parameters in ANN (Artificial Neural Networks)

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dafx

-0.44

ertos

-0.44

 Related

-0.43

ksom

-0.43

 ouvert

-0.43

 sopr

-0.42

酮

-0.42

 open

-0.42

 finalmente

-0.41

 referenties

-0.41

POSITIVE LOGITS

 BorderRadius

0.71

GEBURTSDATUM

0.66

 Majefty

0.66

annica

0.66

tvguidetime

0.64

Efq

0.62

IContainer

0.62

 themſelves

0.61

MessageTagHelper

0.60

 Biôgrafia

0.60

Activations Density 0.479%

references to machine learning techniques and parameters in ANN (Artificial Neural Networks)

No Comments

No Known Activations